© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14934
    Prev
    Next
    INDEX
    Explanations

    words relating to building and the market

    oai_token-act-pair · gemini-2.0-flash

    construction-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    construction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    build
    -0.63
     constru
    -0.60
    Construction
    -0.60
    Build
    -0.60
     Construction
    -0.56
    constru
    -0.56
    Built
    -0.55
     costru
    -0.54
    Construct
    -0.54
     construção
    -0.54
    POSITIVE LOGITS
     typelib
    0.81
    \{\\
    0.73
    TestingModule
    0.69
    astify
    0.69
     незавершена
    0.69
     ProtoMessage
    0.67
    webElementXpaths
    0.67
    ItemSelected
    0.63
    ELTS
    0.63
    tagHelperRunner
    0.62
    Activations Density 2.340%

    No Known Activations